Metraipolis › archive › dc_230bf04577db

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation — arXiv:2510.22115

Source: arXiv (en)
Original: https://arxiv.org/abs/2510.22115
License (as archived): CC0-1.0
Archived: 2026-10-16T07:24:47.230Z
SHA-256 of the archived text: ae92fc7326ff0a72b31b19ba1eb539e447398ee88a2228478e4a7844bcc34d03
Stable URL of this page: https://metraipolis.com/documento/dc_230bf04577db

How to cite

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation — arXiv:2510.22115 — arXiv (en), https://arxiv.org/abs/2510.22115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_230bf04577db (Metraipolis archive dc_230bf04577db, sha256 ae92fc7326ff0a72b31b19ba1eb539e447398ee88a2228478e4a7844bcc34d03)

BibTeX

@misc{dc230bf04577db,
  title = {Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation — arXiv:2510.22115},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2510.22115},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_230bf04577db; sha256 ae92fc7326ff0a72b31b19ba1eb539e447398ee88a2228478e4a7844bcc34d03},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2510.22115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2510.22115 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:00:16.264Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).